lora merged needs about 2.8 GB of memory at Q2_K (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
lora merged is a 3.21B-parameter Lora model in GGUF format, quantized by astegaras. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.4 GB (Q2_K) to 1.4 GB (Q2_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 2.8 GB | Fits | Get file → |
What GPU do you need for lora merged?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q2_K (1.4 GB file, about 2.8 GB in use).
Which lora merged quant should you choose?
Q2_K (1.4 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about lora merged
How much VRAM does lora merged need?
About 2.8 GB at Q2_K with an 8K context window. That is the 1.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run lora merged on an 8 GB GPU?
Yes, with Q2_K: the 1.4 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of lora merged GGUF?
It depends on the quant: Q2_K is 1.4 GB.
What context length does lora merged support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download lora merged GGUF?
The files are on Hugging Face in the astegaras/lora_merged repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.